Impact

Safety Vulnerabilities

Security concerns affecting AI safety and alignment

5 matching entries out of 781 in this category

Safety research results

5 entries

No-Prompt Reasoning Hijack

Updated 4/10/2026

An implicit reasoning hijacking vulnerability exists in Retrieval-Augmented Generation (RAG) and LLM-based agent frameworks. Attackers with write access to an agent's external memory or knowledge base can inject adversarially optimized malicious instances that trigger jailbreaks without requiring any modifications to the user's input prompt. The attack utilizes a shadow model to extract high-contribution subword tokens from anticipated benign user queries via log-probability changes and…

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

Affects: GPT-3.5 Turbo, GPT-4o, GPT-5 +4 more

Source: arXiv

Latent Space Discontinuity Exploitation

Updated 12/5/2025

A vulnerability exists in certain Large Language Models and diffusion models due to discontinuities in their latent space, which arise from data sparsity during training. An attacker can craft inputs containing lexically rare or semantically ambiguous constructs to guide the model's inference process toward these unstable, poorly-conditioned regions. This technique, termed "Alignment Degradation Induction," can degrade or bypass safety alignment mechanisms. Through iterative, multi-turn…

Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks

Source: arXiv

Physical Agent Object Misdirection

Updated 1/14/2026

AdvEDM reveals a vulnerability in Vision-Language Model (VLM) based Embodied Decision-Making (EDM) systems, such as those used in autonomous driving and robotic manipulation. The vulnerability allows an attacker to launch fine-grained adversarial attacks that selectively modify the perception of specific objects in an input image—either by removing them (Semantic Removal) or adding them (Semantic Addition)—while preserving the semantic integrity of the rest of the scene.

AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents

Affects: BLIP-2, MiniGPT-4, LLaVA-v2 +5 more

Source: arXiv

AD Black-Box Cascading Disruption

Updated 12/9/2025

Vision Language Models (VLMs) integrated into autonomous driving (AD) systems are vulnerable to a black-box adversarial attack method termed Cascading Adversarial Disruption (CAD). The vulnerability stems from the model's susceptibility to optimized visual perturbations that disrupt the decision-making reasoning chain (perception, prediction, and planning). Attackers can generate adversarial images or physical patches by aligning visual noise with deceptive textual semantics in the model's…

Black-box adversarial attack on vision language models for autonomous driving

Affects: GPT-4, GPT-4o, InstructBLIP

Source: arXiv

Agent Action Hijacking

Updated 3/19/2025

A vulnerability in LLM-based agents, dubbed AI Agent Injection (AI²), allows attackers to hijack the agent's actions by manipulating the agent's memory retrieval mechanism. The attack involves two main steps: (1) Stealing action-aware knowledge from the agent's memory using crafted adversarial queries targeting the retriever module and (2) Generating Trojan prompts consisting of a Trojan string and hijacking instructions. The Trojan string is designed to manipulate the retriever into…

Towards Action Hijacking of Large Language Model-based Agent

Affects: Alpaca, BERT, GPT-3 +3 more

Source: arXiv

Related research categories